Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6976
    Prev
    Next
    INDEX
    Explanations

    words related to legal definitions related to official purposes

    oai_token-act-pair · gemini-2.0-flash

    differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.74
    antMatchers
    -0.69
     通販
    -0.68
    ########.
    -0.67
     ivelany
    -0.66
     autorytatywna
    -0.63
    <bos>
    -0.60
    routeProvider
    -0.60
     beginnetje
    -0.58
    DllImport
    -0.56
    POSITIVE LOGITS
     Majefty
    0.73
     houſe
    0.66
     Efq
    0.65
     uſe
    0.61
     ſen
    0.60
     ſy
    0.59
     ſur
    0.59
     pleaſure
    0.56
     leſs
    0.56
     ſtre
    0.56
    Activations Density 0.576%

    No Known Activations